Radio Frequency Fingerprinting: Models, Methodologies and Performance

Radio Frequency fingerprinting (RFF) is emerging as a viable alternative to authenticating radio devices, serving as a mitigation technique for spoofing and impersonation attacks on the wireless channel. RFF relies on the observation that each radio transducer features a distinctive radio fingerprint that is impractical - or even impossible - to forge by any other device.In this work, we provide an in-depth analysis of current state-of-the-art RFF approaches by comparing deep learning techniques and the associated methodologies. We consider real measurements in a controlled scenario and compare different configurations and classifiers in terms of performance and training time. Our findings show that the performance of the 11 considered classifiers is significantly biased by the methodology considered during the selection of the data for the training and testing datasets. Training and testing on different measurements or when radios are power-cycled significantly affects the accuracy of the classifier. Overall, our investigation sheds light on best practices and configurations to be considered to maximize the performance of RFF systems deployed in the wild.